README.md

metadata

license: apache-2.0
pipeline_tag: robotics
library_name: lerobot

π₀ (Pi0)

These weights directly come from the Pytorch conversion script of openpi and their pi0_base model.

π₀ is a Vision-Language-Action model for general robot control, from Physical Intelligence. The LeRobot implementation is adapted from their open source OpenPI repository.

---

Paper: Robot Learning: A Tutorial Abstract: Robot learning is at an inflection point, driven by rapid advancements in machine learning and the growing availability of large-scale robotics data. This shift from classical, model-based methods to data-driven, learning-based paradigms is unlocking unprecedented capabilities in autonomous systems. This tutorial navigates the landscape of modern robot learning, charting a course from the foundational principles of Reinforcement Learning and Behavioral Cloning to generalist, language-conditioned models capable of operating across diverse tasks and even robot embodiments. This work is intended as a guide for researchers and practitioners, and our goal is to equip the reader with the conceptual understanding and practical tools necessary to contribute to developments in robot learning, with ready-to-use examples implemented in lerobot. Project Page: https://huggingface.co/spaces/lerobot/robot-learning-tutorial Code for Tutorial: https://github.com/fracapuano/robot-learning-tutorial Original Repository (OpenPI): https://github.com/Physical-Intelligence/openpi

Model Overview

π₀ represents a breakthrough in robotics as the first general-purpose robot foundation model developed by Physical Intelligence. Unlike traditional robots that are narrow specialists programmed for repetitive motions, π₀ is designed to be a generalist policy that can understand visual inputs, interpret natural language instructions, and control a variety of different robots across diverse tasks. This model is featured as an example in the "Robot Learning: A Tutorial" paper.

Architecture and Approach

π₀ combines several key innovations:

• Flow Matching: Uses a novel method to augment pre-trained VLMs with continuous action outputs via flow matching (a variant of diffusion models)
• Cross-Embodiment Training: Trained on data from 8 distinct robot platforms including UR5e, Bimanual UR5e, Franka, Bimanual Trossen, Bimanual ARX, Mobile Trossen, and Mobile Fibocom
• Internet-Scale Pre-training: Inherits semantic knowledge from a pre-trained 3B parameter Vision-Language Model
• High-Frequency Control: Outputs motor commands at up to 50 Hz for real-time dexterous manipulation

Training

For training π₀, you can use the standard LeRobot training script with the appropriate configuration:

python src/lerobot/scripts/train.py \
    --dataset.repo_id=your_dataset \
    --policy.type=pi0 \
    --output_dir=./outputs/pi0_training \
    --job_name=pi0_training \
    --policy.pretrained_path=pepijn223/pi0_base \
    --policy.repo_id=your_repo_id \
    --policy.compile_model=true \
    --policy.gradient_checkpointing=true \
    --policy.dtype=bfloat16 \
    --steps=3000 \
    --policy.scheduler_decay_steps=3000 \
    --policy.device=cuda \
    --batch_size=32

Citation

If you use this model, please cite the original OpenPI work and the tutorial paper:

@article{openpi2024,
    title={Open-World Robotic Manipulation with Vision-Language-Action Models},
    author={Physical Intelligence},
    year={2024},
    url={https://github.com/Physical-Intelligence/openpi}
}

@misc{tutorial2025robotlearning,
      title={Robot Learning: A Tutorial},
      author={Francisco Cruz and Niels Rogge and Victor Dibia and Sasha Bozhkov and Thomas Wolf},
      year={2025},
      eprint={2510.12403},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2510.12403},
}

License

This model follows the same license as the original OpenPI repository, which is Apache 2.0.